# Diverse Sampling for Self-Supervised Learning of Semantic Segmentation

Source: [Diverse Sampling for Self-Supervised Learning of Semantic Segmentation](<https://www.sota2.com/research/paper/68fa62fe1e209131ce9fc1ca>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T05:51:52.529Z

Authors: Mohammadreza Mostajabi, Nicholas Kolkin, Gregory Shakhnarovich

Published: 2016-12-06T20:54:18.000Z

## Abstract

We propose an approach for learning category-level semantic segmentation purely from image-level classification tags indicating presence of categories. It exploits localization cues that emerge from training classification-tasked convolutional networks, to drive a "self-supervision" process that automatically labels a sparse, diverse training set of points likely to belong to classes of interest. Our approach has almost no hyperparameters, is modular, and allows for very fast training of segmentation in less than 3 minutes. It obtains competitive results on the VOC 2012 segmentation benchmark. More, significantly the modularity and fast training of our framework allows new classes to efficiently added for inference.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1612.01991>)

[PDF](<https://arxiv.org/pdf/1612.01991.pdf>)